mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-27 03:44:35 +00:00
75207b3a88
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-musa.Dockerfile platforms:linux/amd64 tag:full-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-musa.Dockerfile platforms:linux/amd64 tag:light-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-musa.Dockerfile platforms:linux/amd64 tag:server-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
37 lines
1.2 KiB
Docker
37 lines
1.2 KiB
Docker
ARG UBUNTU_VERSION=22.04
|
|
# This needs to generally match the container host's environment.
|
|
ARG MUSA_VERSION=rc3.1.0
|
|
# Target the MUSA build image
|
|
ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
|
# Target the MUSA runtime image
|
|
ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
|
|
|
|
FROM ${BASE_MUSA_DEV_CONTAINER} AS build
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y build-essential git cmake libcurl4-openssl-dev
|
|
|
|
WORKDIR /app
|
|
|
|
COPY . .
|
|
|
|
RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
|
cmake --build build --config Release --target llama-server -j$(nproc) && \
|
|
mkdir -p /app/lib && \
|
|
find build -name "*.so" -exec cp {} /app/lib \;
|
|
|
|
FROM ${BASE_MUSA_RUN_CONTAINER} AS runtime
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y libcurl4-openssl-dev libgomp1 curl
|
|
|
|
COPY --from=build /app/lib/ /
|
|
COPY --from=build /app/build/bin/llama-server /llama-server
|
|
|
|
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
|
ENV LLAMA_ARG_HOST=0.0.0.0
|
|
|
|
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
|
|
|
ENTRYPOINT [ "/llama-server" ]
|